{"total":21,"rows":[{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"area":"alignment"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2409.17401","title":"Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference","created":"2024-09-25","cited_by_count":12,"area":"alignment"},{"id":"2412.16878","title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","created":"2024-12-22","cited_by_count":7,"area":"alignment"},{"id":"2410.04503","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs","created":"2024-10-06","cited_by_count":5,"area":"alignment"},{"id":"2406.06874","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2406.14457","title":"Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue","created":"2024-06-20","cited_by_count":3,"area":"alignment"},{"id":"2203.04951","title":"Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation Method","created":"2022-03-09","cited_by_count":2,"area":"alignment"},{"id":"2308.15969","title":"Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification","created":"2023-08-30","cited_by_count":2,"area":"alignment"},{"id":"2407.10839","title":"Offline Reinforcement Learning with Imputed Rewards","created":"2024-07-15","cited_by_count":2,"area":"alignment"},{"id":"2604.19024","title":"Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","cited_by_count":1,"area":"alignment"},{"id":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"id":"2406.16258","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2509.22807","title":"MTRec: Learning to Align with User Preferences via Mental Reward Models","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2408.05610","title":"Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations","created":"2024-08-10","cited_by_count":0,"area":"alignment"},{"id":"2601.09236","title":"Reward Learning through Ranking Mean Squared Error","created":"2026-01-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}